library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

Using bult-in datasets

data <- diamonds

Using datasets from pkgs

library(gapminder)
gapminder
## # A tibble: 1,704 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows

import data from the web

ca <- read_csv("https://raw.githubusercontent.com/ScienceParkStudyGroup/r-lesson-based-on-ohi-data-training/gh-pages/data/ca.csv")
## Rows: 789 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): region, state, code, park_name, type
## dbl (2): visitors, year
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Explore dataset

glimpse(ca)
## Rows: 789
## Columns: 7
## $ region    <chr> "PW", "PW", "PW", "PW", "PW", "PW", "PW", "PW", "PW", "PW", …
## $ state     <chr> "CA", "CA", "CA", "CA", "CA", "CA", "CA", "CA", "CA", "CA", …
## $ code      <chr> "CHIS", "CHIS", "CHIS", "CHIS", "CHIS", "CHIS", "CHIS", "CHI…
## $ park_name <chr> "Channel Islands National Park", "Channel Islands National P…
## $ type      <chr> "National Park", "National Park", "National Park", "National…
## $ visitors  <dbl> 1200, 1500, 1600, 300, 15700, 31000, 33100, 32000, 24400, 31…
## $ year      <dbl> 1963, 1964, 1965, 1966, 1967, 1968, 1969, 1970, 1971, 1972, …

1st Plot

ggplot(ca, aes(x = year, y = visitors, colour = park_name)) +
  geom_point(alpha = 0.5) +
  labs( x= "Year", y= "Visitors", title= "California National Park Visitation" ) +
  theme_minimal() +
  theme(
    legend.title = element_blank()
  )

ggplot(ca, aes(x = year, y = visitors)) +
  geom_point(alpha = 0.5, ) +
  theme_light() 

unique(ca$state)
## [1] "CA"

Gap minder data

library(gapminder)
library(tidyverse)

gapminder <- gapminder

ggplot(gapminder, aes(x = log(gdpPercap),col= year, y = lifeExp, size = pop)) +
  geom_point(alpha= 0.3, color = "#8d228d") +
  geom_smooth(method = lm) +
  facet_wrap(~continent, scales = "free") +
  theme_bw() 
## `geom_smooth()` using formula 'y ~ x'

## Ex.

library(tidyverse)
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
data <- read_csv("https://raw.githubusercontent.com/ScienceParkStudyGroup/r-lesson-based-on-ohi-data-training/gh-pages/data/se.csv")
## Rows: 453 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): region, state, code, park_name, type
## dbl (2): visitors, year
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
plot <- ggplot(data, aes(x = park_name, y = visitors,  col = park_name)) +
  geom_boxplot() +
  geom_jitter(alpha = .3) +
  coord_flip() +
  theme_bw() +
  theme(
    legend.position = "none"
  )

ggplotly(plot)